├── src
    ├── unistring_app.erl
    └── unistring.app.src
├── .gitignore
├── rebar.config
├── Makefile
├── test
    └── unistring_tests.erl
└── README.md


/src/unistring_app.erl:
--------------------------------------------------------------------------------
1 | -module(unistring_app).
2 | -vsn("0.1.0").


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | .eunit
2 | deps
3 | *.o
4 | *.beam
5 | *.plt
6 | *.dump
7 | ebin/*.*


--------------------------------------------------------------------------------
/rebar.config:
--------------------------------------------------------------------------------
1 | {erl_opts, [fail_on_warning, debug_info]}.
2 | {cover_enabled, true}.
3 | {clean_files, ["*.eunit", "ebin/*.beam"]}.


--------------------------------------------------------------------------------
/Makefile:
--------------------------------------------------------------------------------
 1 | REBAR:=rebar
 2 | 
 3 | .PHONY: all erl test clean doc 
 4 | 
 5 | all: erl
 6 | 
 7 | erl:
 8 | 	$(REBAR) get-deps compile
 9 | 
10 | test: all
11 | 	@mkdir -p .eunit
12 | 	$(REBAR) skip_deps=true eunit
13 | 
14 | clean:
15 | 	$(REBAR) clean
16 | 	-rm -rvf deps ebin doc .eunit
17 | 
18 | doc:
19 | 	$(REBAR) doc
20 | 


--------------------------------------------------------------------------------
/src/unistring.app.src:
--------------------------------------------------------------------------------
 1 | {application, unistring,
 2 |  [
 3 |   {description, "Unicode utf-8 functions"},
 4 |   {vsn, "0.1.0"},
 5 |   {registered, []},
 6 |   {applications, [
 7 |                   kernel,
 8 |                   stdlib
 9 |                  ]},
10 |   {mod, { unistring_app, []}},
11 |   {env, []}
12 |  ]}.
13 | 


--------------------------------------------------------------------------------
/test/unistring_tests.erl:
--------------------------------------------------------------------------------
 1 | %% -*- coding: utf-8 -*-
 2 | -module(unistring_tests).
 3 | -include_lib("eunit/include/eunit.hrl").
 4 | 
 5 | to_lower_test() ->
 6 | 	?assertEqual("test", unistring:to_lower("TEST")),
 7 | 	?assertEqual(<<"test">>, unistring:to_lower(<<"TEST">>)),
 8 | 	?assertEqual("привет", unistring:to_lower("ПРИВЕТ")),
 9 | 	?assertEqual(<<"привет"/utf8>>, unistring:to_lower(<<"ПРИВЕТ"/utf8>>)).
10 | 
11 | to_upper_test() ->
12 | 	?assertEqual("TEST", unistring:to_upper("test")),
13 | 	?assertEqual(<<"TEST">>, unistring:to_upper(<<"test">>)),
14 | 	?assertEqual("ПРИВЕТ", unistring:to_upper("привет")),
15 | 	?assertEqual(<<"ПРИВЕТ"/utf8>>, unistring:to_upper(<<"привет"/utf8>>)).


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | #unistring
 2 | =========
 3 | 
 4 | ##Why
 5 | Starting with Erlang **R16B**, [string module](http://www.erlang.org/doc/man/string.html) in standard library handles Unicode utf-8 strings very well, except that ```string:to_upper/1``` and ```string:to_lower/1``` ignore unicode code points > 255. 
 6 | 
 7 | Unistring library uses Lowercase Mapping, Uppercase Mapping and Titlecase Mapping columns hexadecimal values from [UnicodeData.txt](ftp://ftp.unicode.org/Public/UNIDATA/UnicodeData.txt).
 8 | 
 9 | ##License
10 | Public Domain
11 | 
12 | ##API
13 | Unicode utf-8 functions for Erlang:
14 | 
15 | ```erlang
16 | unistring:to_lower/1
17 | unistring:to_upper/1
18 | unistring:to_title/1
19 | ```
20 | 
21 | Input to functions can be in ```charlist()``` or ```unicode_binary()``` format.
22 | 
23 | charlist() is a list of unicode code points, such as: ```[50504,45397,54616,49464,50836]``` means ```"안녕하세요"```.
24 | unicode_binary() is a binary string with utf8 encoding, such as: ```<<236,149,136,235,133,149,237,149,152,236,132,184,236,154,148>>``` means ```"안녕하세요"```.
25 | 
26 | charlist() and unicode_binary() can be converted from one to another using the [unicode module](http://www.erlang.org/doc/man/unicode.html) in Erlang **R16B** or later.
27 | 
28 | ##Examples
29 | Make sure to start your erl shell with ```erl +pc unicode```
30 | Make sure to add ```%% -*- coding: utf-8 -*-``` to the beginning of your ```*.erl``` source code files if you will be using unicode characters inside of quotes.
31 | If you are creating unicode binary strings, make sure to append **/utf8** after the string's end quote mark inside of <<>> such as: ```<<"안녕하세요"/utf8>>.
32 | 
33 | ```erlang
34 | %% unistring:to_lower/1
35 | 
36 | "test" = unistring:to_lower("TEST").
37 | <<"test">> = unistring:to_lower(<<"TEST">>).
38 | "привет" = unistring:to_lower("ПРИВЕТ").
39 | <<"привет"/utf8>> = unistring:to_lower(<<"ПРИВЕТ"/utf8>>).
40 | 
41 | %% unistring:to_upper/1
42 | "TEST" = unistring:to_upper("test").
43 | <<"TEST">> = unistring:to_upper(<<"test">>).
44 | "ПРИВЕТ" = unistring:to_upper("привет").
45 | <<"ПРИВЕТ"/utf8>> = unistring:to_upper(<<"привет"/utf8>>).
46 | ```
47 | 
48 | ##Note
49 | I don't really see the point of ```unistring:to_title/1``` but it is included in this library for completeness.


--------------------------------------------------------------------------------